© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112011
    Prev
    Next
    INDEX
    Explanations

    attract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stren
    -0.11
     Bun
    -0.10
     renov
    -0.10
    manuel
    -0.09
     gulp
    -0.09
    elines
    -0.09
    ibur
    -0.09
     repet
    -0.09
     Scho
    -0.09
     Laud
    -0.09
    POSITIVE LOGITS
     attracting
    0.52
     attract
    0.50
     attracts
    0.48
     attracted
    0.34
     attraction
    0.32
     lure
    0.30
     deterrent
    0.30
     attractiveness
    0.28
     deter
    0.27
     attractive
    0.25
    Activations Density 0.304%

    No Known Activations